{"id":"W4362676437","doi":"10.1145/3586049","title":"Pushing the Limit of 1-Minimality of Language-Agnostic Program Reduction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Programming language; Reduction (mathematics); Computer science; Syntax; Implementation; Theoretical computer science; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001285646,0.0001578983,0.0002462641,0.0001554078,0.0001221713,0.0000837702,0.002995405,0.00007320812,8.547343e-7],"category_scores_gemma":[0.008172713,0.00009545082,0.0001502571,0.001384289,0.0002298287,0.0001822468,0.001151463,0.000218895,0.000001799467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001972247,"about_ca_system_score_gemma":0.00002988612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001594112,"about_ca_topic_score_gemma":0.000001390959,"domain_scores_codex":[0.9984964,0.00002739566,0.0003852749,0.0003000895,0.0005030544,0.0002878082],"domain_scores_gemma":[0.9977292,0.0005438128,0.0005627114,0.000861008,0.0002690023,0.00003420618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003745773,0.0004043402,0.01913413,0.0008235751,0.00008366144,0.000002982931,0.01713191,0.0000180021,0.02938047,0.006138937,0.006870897,0.9199736],"study_design_scores_gemma":[0.0005523784,0.00173956,0.05689075,0.002438754,0.0001514988,0.00009117721,0.004989866,0.001778608,0.8893945,0.04040604,0.0009683754,0.0005985285],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918861,0.0001971713,0.0001054312,0.002345982,0.0001477282,0.000714815,0.000003016993,0.004171086,0.0004286131],"genre_scores_gemma":[0.9165206,0.00001278158,0.08322207,0.00002555528,0.00004954134,0.0000940577,0.000001150713,0.0000162781,0.00005797724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9193751,"threshold_uncertainty_score":0.9784091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02725027826828869,"score_gpt":0.3119918759498543,"score_spread":0.2847415976815656,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}